PyTorchKR Papers

최신 논문

총 2,063편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2012.11774공식 코드 · Papers with Code

Differentially Private Synthetic Medical Data Generation using Convolutional GANs

Deep learning models have demonstrated superior performance in several application problems, such as image classification and speech processing. However, creating a deep learning model using health record data requires addressing certain privacy challenges that bring unique concerns to researchers working in this domain. One effective way to handle such private data issues is to generate realistic synthetic data that can provide practically acceptable data quality and correspondingly the model performance. To tackle this challenge, we develop a differentially private framework for synthetic data generation using R\'enyi differential privacy. Our approach builds on convolutional autoencoders and convolutional generative adversarial networks to preserve some of the critical characteristics of the generated synthetic data. In addition, our model can also capture the temporal information and feature correlations that might be present in the original data. We demonstrate that our model outperforms existing state-of-the-art models under the same privacy budget using several publicly available benchmark medical datasets in both supervised and unsupervised settings.

arXiv:2012.09284공식 코드 · Papers with Code

Sparse Signal Models for Data Augmentation in Deep Learning ATR

Automatic Target Recognition (ATR) algorithms classify a given Synthetic Aperture Radar (SAR) image into one of the known target classes using a set of training images available for each class. Recently, learning methods have shown to achieve state-of-the-art classification accuracy if abundant training data is available, sampled uniformly over the classes, and their poses. In this paper, we consider the task of ATR with a limited set of training images. We propose a data augmentation approach to incorporate domain knowledge and improve the generalization power of a data-intensive learning algorithm, such as a Convolutional neural network (CNN). The proposed data augmentation method employs a limited persistence sparse modeling approach, capitalizing on commonly observed characteristics of wide-angle synthetic aperture radar (SAR) imagery. Specifically, we exploit the sparsity of the scattering centers in the spatial domain and the smoothly-varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of over-parametrized model fitting. Using this estimated model, we synthesize new images at poses and sub-pixel translations not available in the given data to augment CNN's training data. The experimental results show that for the training data starved region, the proposed method provides a significant gain in the resulting ATR algorithm's generalization performance.

arXiv:2012.07994공식 코드 · Papers with Code

Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model

Anti-malware engines are the first line of defense against malicious software. While widely used, feature engineering-based anti-malware engines are vulnerable to unseen (zero-day) attacks. Recently, deep learning-based static anti-malware detectors have achieved success in identifying unseen attacks without requiring feature engineering and dynamic analysis. However, these detectors are susceptible to malware variants with slight perturbations, known as adversarial examples. Generating effective adversarial examples is useful to reveal the vulnerabilities of such systems. Current methods for launching such attacks require accessing either the specifications of the targeted anti-malware model, the confidence score of the anti-malware response, or dynamic malware analysis, which are either unrealistic or expensive. We propose MalRNN, a novel deep learning-based approach to automatically generate evasive malware variants without any of these restrictions. Our approach features an adversarial example generation process, which learns a language model via a generative sequence-to-sequence recurrent neural network to augment malware binaries. MalRNN effectively evades three recent deep learning-based malware detectors and outperforms current benchmark methods. Findings from applying our MalRNN on a real dataset with eight malware categories are discussed.

arXiv:2012.08452공식 코드 · Papers with Code

Molecular machine learning with conformer ensembles

Virtual screening can accelerate drug discovery by identifying promising candidates for experimental evaluation. Machine learning is a powerful method for screening, as it can learn complex structure-property relationships from experimental data and make rapid predictions over virtual libraries. Molecules inherently exist as a three-dimensional ensemble and their biological action typically occurs through supramolecular recognition. However, most deep learning approaches to molecular property prediction use a 2D graph representation as input, and in some cases a single 3D conformation. Here we investigate how the 3D information of multiple conformers, traditionally known as 4D information in the cheminformatics community, can improve molecular property prediction in deep learning models. We introduce multiple deep learning models that expand upon key architectures such as ChemProp and Schnet, adding elements such as multiple-conformer inputs and conformer attention. We then benchmark the performance trade-offs of these models on 2D, 3D and 4D representations in the prediction of drug activity using a large training set of geometrically resolved molecules. The new architectures perform significantly better than 2D models, but their performance is often just as strong with a single conformer as with many. We also find that 4D deep learning models learn interpretable attention weights for each conformer.

arXiv:2012.08392공식 코드 · Papers with Code

FINED: Fast Inference Network for Edge Detection

In this paper, we address the design of lightweight deep learning-based edge detection. The deep learning technology offers a significant improvement on the edge detection accuracy. However, typical neural network designs have very high model complexity, which prevents it from practical usage. In contrast, we propose a Fast Inference Network for Edge Detection (FINED), which is a lightweight neural net dedicated to edge detection. By carefully choosing proper components for edge detection purpose, we can achieve the state-of-the-art accuracy in edge detection while significantly reducing its complexity. Another key contribution in increasing the inferencing speed is introducing the training helper concept. The extra subnetworks (training helper) are employed in training but not used in inferencing. It can further reduce the model complexity and yet maintain the same level of accuracy. Our experiments show that our systems outperform all the current edge detectors at about the same model (parameter) size.

arXiv:2012.08194공식 코드 · Papers with Code

Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction

The characterization of drug-protein interactions is crucial in the high-throughput screening for drug discovery. The deep learning-based approaches have attracted attention because they can predict drug-protein interactions without trial-and-error by humans. However, because data labeling requires significant resources, the available protein data size is relatively small, which consequently decreases model performance. Here we propose two methods to construct a deep learning framework that exhibits superior performance with a small labeled dataset. At first, we use transfer learning in encoding protein sequences with a pretrained model, which trains general sequence representations in an unsupervised manner. Second, we use a Bayesian neural network to make a robust model by estimating the data uncertainty. As a result, our model performs better than the previous baselines for predicting drug-protein interactions. We also show that the quantified uncertainty from the Bayesian inference is related to the confidence and can be used for screening DPI data points.

arXiv:2012.08026공식 코드 · Papers with Code

Classification of Smoking and Calling using Deep Learning

Since 2014, very deep convolutional neural networks have been proposed and become the must-have weapon for champions in all kinds of competition. In this report, a pipeline is introduced to perform the classification of smoking and calling by modifying the pretrained inception V3. Brightness enhancing based on deep learning is implemented to improve the classification of this classification task along with other useful training tricks. Based on the quality and quantity results, it can be concluded that this pipeline with small biased samples is practical and useful with high accuracy.

arXiv:2012.06690공식 코드 · Papers with Code

Yelp Review Rating Prediction: Machine Learning and Deep Learning Models

We predict restaurant ratings from Yelp reviews based on Yelp Open Dataset. Data distribution is presented, and one balanced training dataset is built. Two vectorizers are experimented for feature engineering. Four machine learning models including Naive Bayes, Logistic Regression, Random Forest, and Linear Support Vector Machine are implemented. Four transformer-based models containing BERT, DistilBERT, RoBERTa, and XLNet are also applied. Accuracy, weighted F1 score, and confusion matrix are used for model evaluation. XLNet achieves 70% accuracy for 5-star classification compared with Logistic Regression with 64% accuracy.

arXiv:2012.05549공식 코드 · Papers with Code

Categorical Perception: A Groundwork for Deep Learning

A well-known perceptual consequence of categorization in humans and other animals, called categorical perception, is notably characterized by a within-category compression and a between-category separation: two items, close in input space, are perceived closer if they belong to the same category than if they belong to different categories. Elaborating on experimental and theoretical results in cognitive science, here we study categorical effects in artificial neural networks. We combine a theoretical analysis that makes use of mutual and Fisher information quantities, and a series of numerical simulations on networks of increasing complexity. These formal and numerical analyses provide insights into the geometry of the neural representation in deep layers, with expansion of space near category boundaries and contraction far from category boundaries. We investigate categorical representation by using two complementary approaches: one mimics experiments in psychophysics and cognitive neuroscience by means of morphed continua between stimuli of different categories, while the other introduces a categoricality index that, for each layer in the network, quantifies the separability of the categories at the neural population level. We show on both shallow and deep neural networks that category learning automatically induces categorical perception. We further show that the deeper a layer, the stronger the categorical effects. As an outcome of our study, we propose a coherent view of the efficacy of different heuristic practices of the dropout regularization technique. More generally, our view, which finds echoes in the neuroscience literature, insists on the differential impact of noise in any given layer depending on the geometry of the neural representation that is being learned, i.e. on how this geometry reflects the structure of the categories.

arXiv:2012.05322공식 코드 · Papers with Code

Deep Learning Segmentation of Complex Features in Atomic-Resolution Phase Contrast Transmission Electron Microscopy Images

Phase contrast transmission electron microscopy (TEM) is a powerful tool for imaging the local atomic structure of materials. TEM has been used heavily in studies of defect structures of 2D materials such as monolayer graphene due to its high dose efficiency. However, phase contrast imaging can produce complex nonlinear contrast, even for weakly-scattering samples. It is therefore difficult to develop fully-automated analysis routines for phase contrast TEM studies using conventional image processing tools. For automated analysis of large sample regions of graphene, one of the key problems is segmentation between the structure of interest and unwanted structures such as surface contaminant layers. In this study, we compare the performance of a conventional Bragg filtering method to a deep learning routine based on the U-Net architecture. We show that the deep learning method is more general, simpler to apply in practice, and produces more accurate and robust results than the conventional algorithm. We provide easily-adaptable source code for all results in this paper, and discuss potential applications for deep learning in fully-automated TEM image analysis.

arXiv:2012.04885공식 코드 · Papers with Code

Annotation-efficient deep learning for automatic medical image segmentation

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, we introduce Annotation-effIcient Deep lEarning (AIDE), an open-source framework to handle imperfect training datasets. Methodological analyses and empirical evaluations are conducted, and we demonstrate that AIDE surpasses conventional fully-supervised models by presenting better performance on open datasets possessing scarce or noisy annotations. We further test AIDE in a real-life case study for breast tumor segmentation. Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated by fully-supervised counterparts or provided by independent radiologists. The 10-fold enhanced efficiency in utilizing expert labels has the potential to promote a wide range of biomedical applications.

arXiv:2012.04575공식 코드 · Papers with Code

The Role of Interpretable Patterns in Deep Learning for Morphology

We examine the role of character patterns in three tasks: morphological analysis, lemmatization and copy. We use a modified version of the standard sequence-to-sequence model, where the encoder is a pattern matching network. Each pattern scores all possible N character long subwords (substrings) on the source side, and the highest scoring subword's score is used to initialize the decoder as well as the input to the attention mechanism. This method allows learning which subwords of the input are important for generating the output. By training the models on the same source but different target, we can compare what subwords are important for different tasks and how they relate to each other. We define a similarity metric, a generalized form of the Jaccard similarity, and assign a similarity score to each pair of the three tasks that work on the same source but may differ in target. We examine how these three tasks are related to each other in 12 languages. Our code is publicly available.

arXiv:2012.04407공식 코드 · Papers with Code

Enhanced spatio-temporal electric load forecasts using less data with active deep learning

An effective way to oppose global warming and mitigate climate change is to electrify our energy sectors and supply their electric power from renewable wind and solar. Spatio-temporal predictions of electric load become increasingly important for planning this transition, while deep learning prediction models provide increasingly accurate predictions for it. The data used for training deep learning models, however, is usually collected at random using a passive learning approach. This naturally results in a large demand for data and associated costs for sensors like smart meters, posing a large barrier for electric utilities in decarbonizing their grids. Here, we test active learning where we leverage additional computation for collecting a more informative subset of data. We show how electric utilities can apply active learning to better distribute smart meters and collect their data for more accurate predictions of load with about half the data compared to when applying passive learning.

arXiv:2012.03324공식 코드 · Papers with Code

Align-gram : Rethinking the Skip-gram Model for Protein Sequence Analysis

Background: The inception of next generations sequencing technologies have exponentially increased the volume of biological sequence data. Protein sequences, being quoted as the `language of life', has been analyzed for a multitude of applications and inferences. Motivation: Owing to the rapid development of deep learning, in recent years there have been a number of breakthroughs in the domain of Natural Language Processing. Since these methods are capable of performing different tasks when trained with a sufficient amount of data, off-the-shelf models are used to perform various biological applications. In this study, we investigated the applicability of the popular Skip-gram model for protein sequence analysis and made an attempt to incorporate some biological insights into it. Results: We propose a novel $k$-mer embedding scheme, Align-gram, which is capable of mapping the similar $k$-mers close to each other in a vector space. Furthermore, we experiment with other sequence-based protein representations and observe that the embeddings derived from Align-gram aids modeling and training deep learning models better. Our experiments with a simple baseline LSTM model and a much complex CNN model of DeepGoPlus shows the potential of Align-gram in performing different types of deep learning applications for protein sequence analysis.

arXiv:2012.02775공식 코드 · Papers with Code

Representation Based Complexity Measures for Predicting Generalization in Deep Learning

Deep Neural Networks can generalize despite being significantly overparametrized. Recent research has tried to examine this phenomenon from various view points and to provide bounds on the generalization error or measures predictive of the generalization gap based on these viewpoints, such as norm-based, PAC-Bayes based, and margin-based analysis. In this work, we provide an interpretation of generalization from the perspective of quality of internal representations of deep neural networks, based on neuroscientific theories of how the human visual system creates invariant and untangled object representations. Instead of providing theoretical bounds, we demonstrate practical complexity measures which can be computed ad-hoc to uncover generalization behaviour in deep models. We also provide a detailed description of our solution that won the NeurIPS competition on Predicting Generalization in Deep Learning held at NeurIPS 2020. An implementation of our solution is available at https://github.com/parthnatekar/pgdl.

arXiv:2012.02732공식 코드 · Papers with Code

Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning

Deep learning (DL) frameworks take advantage of GPUs to improve the speed of DL inference and training. Ideally, DL frameworks should be able to fully utilize the computation power of GPUs such that the running time depends on the amount of computation assigned to GPUs. Yet, we observe that in scheduling GPU tasks, existing DL frameworks suffer from inefficiencies such as large scheduling overhead and unnecessary serial execution. To this end, we propose Nimble, a DL execution engine that runs GPU tasks in parallel with minimal scheduling overhead. Nimble introduces a novel technique called ahead-of-time (AoT) scheduling. Here, the scheduling procedure finishes before executing the GPU kernel, thereby removing most of the scheduling overhead during run time. Furthermore, Nimble automatically parallelizes the execution of GPU tasks by exploiting multiple GPU streams in a single GPU. Evaluation on a variety of neural networks shows that compared to PyTorch, Nimble speeds up inference and training by up to 22.34$\times$ and 3.61$\times$, respectively. Moreover, Nimble outperforms state-of-the-art inference systems, TensorRT and TVM, by up to 2.81$\times$ and 1.70$\times$, respectively.

arXiv:2012.02260공식 코드 · Papers with Code

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems (ITS), in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular ITS research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field.

arXiv:2012.01598공식 코드 · Papers with Code

Graph Neural Networks for Improved El Niño Forecasting

Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Ni\~no-Southern Oscillation (ENSO). However, current deep learning models are based on convolutional neural networks which are difficult to interpret and can fail to model large-scale atmospheric patterns called teleconnections. Hence, we propose the application of spatiotemporal Graph Neural Networks (GNN) to forecast ENSO at long lead times, finer granularity and improved predictive skill than current state-of-the-art methods. The explicit modeling of information flow via edges may also allow for more interpretable forecasts. Preliminary results are promising and outperform state-of-the art systems for projections 1 and 3 months ahead.

arXiv:2007.10462공식 코드 · Papers with Code

Deep Local Volatility

Deep learning for option pricing has emerged as a novel methodology for fast computations with applications in calibration and computation of Greeks. However, many of these approaches do not enforce any no-arbitrage conditions, and the subsequent local volatility surface is never considered. In this article, we develop a deep learning approach for interpolation of European vanilla option prices which jointly yields the full surface of local volatilities. We demonstrate the modification of the loss function or the feed forward network architecture to enforce (hard constraints approach) or favor (soft constraints approach) the no-arbitrage conditions and we specify the experimental design parameters that are needed for adequate performance. A novel component is the use of the Dupire formula to enforce bounds on the local volatility associated with option prices, during the network fitting. Our methodology is benchmarked numerically on real datasets of DAX vanilla options.

arXiv:2006.14540공식 코드 · Papers with Code

Graph Convolutional Neural Networks for analysis of EEG signals, BCI application

Decoding brain signals has gained many attention and has found much applications in recent years such as Brain Computer Interfaces, communicating with controlling external devices using the user's intentions, occupies an emerging field with the potential of changing the world, with diverse applications from rehabilitation to human augmentation. This being said brain signal analysis, EEG brain signal analysis in particular, is a challenging task. With the advances and achievements in the field of deep learning in problem solving with using only raw data, few attempts has been carried in recent years, to apply deep learning to tackle EEG among other types of brain signals. In this study, we propose a novel loss function, called DeepCSP to extend the classical Common Spatial Patterns to a non linear, differentiable module to serve as the loss function to enforce linearly separable latent representations of EEG signals belonging to different classes in an end to end manner on raw signals without the need to perform extensive feature engineering. With recent generalizations of deep learning methods to work on arbitrarily structured graphs and the introduced loss we have proposed two light weight models to decode EEG signals and carried experiments to show their performance.